Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Prediction of protein structural class using novel evolutionary collocation-based sequence representation.

Ke Chen1, Lukasz A Kurgan, Jishou Ruan

  • 1Department of Electrical and Computer Engineering, ECERF, University of Alberta, Edmonton, Alberta, Canada.

Journal of Computational Chemistry
|February 23, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Precise annotation of Drosophila mitochondrial genomes leads to insights into AT-rich regions.

Mitochondrion·2022
Same author

How the Replication and Transcription Complex Functions in Jumping Transcription of SARS-CoV-2.

Frontiers in genetics·2022
Same author

Full-Length Genome of an <i>Ogataea polymorpha</i> Strain CBS4732 <i>ura3</i>Δ Reveals Large Duplicated Segments in Subtelomeric Regions.

Frontiers in microbiology·2022
Same author

Genomic Feature Analysis of Betacoronavirus Provides Insights Into SARS and COVID-19 Pandemics.

Frontiers in microbiology·2021
Same author

A Negative Feedback Model to Explain Regulation of SARS-CoV-2 Replication and Transcription.

Frontiers in genetics·2021
Same author

Probabilistic analysis of the frequencies of amino acid pairs within characterized protein sequences.

Physica A·2020
Same journal

How Do DICER1 Syndrome Mutations Disrupt Catalysis? Unveiling Dicer Metal Binding Architecture and Mechanism of Action Using MD Simulations and QM/MM Calculations.

Journal of computational chemistry·2026
Same journal

Quadruple Bonding of Alkaline Earth Atoms in AeCLi<sub>4</sub> (Ae = Be - Ba) Complexes.

Journal of computational chemistry·2026
Same journal

From SMILES Codes for Reactants and Products to Transition States With VeloxChem.

Journal of computational chemistry·2026
Same journal

Electric-Field Effects on Structure and Conductance in a Cytochrome b<sub>562</sub> Junction.

Journal of computational chemistry·2026
Same journal

Quantum Chemistry Study of Luminescence Quenching in the Eu<sup>3+</sup>@UiO-67 Sensor Induced by Ag<sup>+</sup> Ions.

Journal of computational chemistry·2026
Same journal

Projection-Modified Direct Inversion in the Iterative Subspace: A Memory-Efficient Convergence Method for the Extended Molecular Ornstein-Zernike Theory.

Journal of computational chemistry·2026
See all related articles

A new protein sequence representation using evolutionary information significantly improves structural class prediction accuracy. This method reduces error rates by 14-26% compared to existing approaches.

Area of Science:

  • * Computational Biology
  • * Bioinformatics
  • * Structural Bioinformatics

Background:

  • * Understanding protein folding patterns relies on knowledge of structural classes.
  • * Existing protein structural class prediction methods often use simple sequence representations, such as amino acid composition.
  • * There is a need for improved sequence representations that incorporate evolutionary information.

Purpose of the Study:

  • * To propose a novel protein sequence representation incorporating evolutionary information.
  • * To evaluate the effectiveness of this new representation in predicting protein structural classes.
  • * To compare the performance of the proposed method against existing state-of-the-art techniques.

Main Methods:

  • * Developed a novel sequence representation using PSI-BLAST profile-based collocation of amino acid pairs.

Related Experiment Videos

  • * Utilized six benchmark datasets and five representative classifiers (including Support Vector Machine).
  • * Quantified and compared prediction quality using the proposed representation.

    • Main Results:

    • * The Support Vector Machine classifier achieved 61-96% accuracy across six datasets.
    • * The proposed representation demonstrated superiority, reducing error rates by 14-26% compared to previous methods.
    • * Prediction accuracy was notably lower (20-35%) for datasets with low sequence identity (25-40%).

    Conclusions:

    • * The novel sequence representation substantially improves the accuracy of protein structural class prediction.
    • * The method's effectiveness is validated across multiple datasets and classifiers.
    • * A web server implementing the prediction method is available for public use.